Updated March 26, 2026· Based on independent benchmark data
Gemini 3 Pro Preview (high) and GPT-5.4 mini (xhigh) are virtually tied on intelligence (48.4 vs 48.1). GPT-5.4 mini (xhigh) is 2.7x cheaper at $0.75/1M tokens vs $2.00/1M. For speed, GPT-5.4 mini (xhigh) wins at 218 tok/s vs 115 tok/s.
| Metric | Gemini 3 Pro Preview (high) | GPT-5.4 mini (xhigh) |
|---|---|---|
| Intelligence Score | 48.4 | 48.1 |
| Coding Score | 46.5 | 51.5 |
| Math Score | 95.7 | N/A |
| Speed (tok/s) | 115 tok/s | 218 tok/s |
| Latency (TTFT) | 36.25s | 7.45s |
| Input Price / 1M tokens | $2.00 | $0.75 |
| Output Price / 1M tokens | $12 | $4.50 |
| Context Window | N/A |
Gemini 3 Pro Preview (high) and GPT-5.4 mini (xhigh) perform similarly on overall intelligence, scoring 48.4 and 48.1 respectively. For coding tasks, GPT-5.4 mini (xhigh) has the edge with a coding score of 51.5 vs 46.5.
GPT-5.4 mini (xhigh) generates output significantly faster at 218 tok/s compared to Gemini 3 Pro Preview (high)'s 115 tok/s, making it 1.9x faster for streaming responses. Time to first token is 7.45s for GPT-5.4 mini (xhigh) vs 36.25s for Gemini 3 Pro Preview (high), which affects perceived responsiveness in interactive applications.
GPT-5.4 mini (xhigh) is more affordable at $0.75/1M input tokens ($4.50/1M output), while Gemini 3 Pro Preview (high) costs $2.00/1M input ($12/1M output). That makes Gemini 3 Pro Preview (high) 2.7x more expensive per token, which can add up significantly at scale. For a typical workload of 100 requests per day at 2,000 tokens each, Gemini 3 Pro Preview (high) would cost approximately $12.00/month vs $4.50/month for GPT-5.4 mini (xhigh) in input costs alone.
Choose GPT-5.4 mini (xhigh) when you need stronger coding performance (51.5), faster output (218 tok/s), lower cost.
GPT-5.4 mini (xhigh) scores higher on coding benchmarks (51.5 vs 46.5), making it the better choice for programming tasks.
GPT-5.4 mini (xhigh) is cheaper at $0.75/1M input tokens vs $2.00/1M for Gemini 3 Pro Preview (high).
GPT-5.4 mini (xhigh) is faster, producing output at 218 tok/s compared to Gemini 3 Pro Preview (high)'s 115 tok/s.
No, Gemini 3 Pro Preview (high) does not support image input. Neither model supports image input.
Data last synced: March 26, 2026
| N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
| Output Modalities | Text | Text |
| Free Tier | No | No |
Both models perform similarly on intelligence benchmarks. Choose based on specific needs: pricing, speed, context window, or provider ecosystem.